sched/fair: Search a task from the tail of the queue

As a first step this patch makes cfs_tasks list as MRU one.
It means, that when a next task is picked to run on physical
CPU it is moved to the front of the list.

Therefore, the cfs_tasks list is more or less sorted (except
woken tasks) starting from recently given CPU time tasks toward
tasks with max wait time in a run-queue, i.e. MRU list.

Second, as part of the load balance operation, this approach
starts detach_tasks()/detach_one_task() from the tail of the
queue instead of the head, giving some advantages:

 - tends to pick a task with highest wait time;

 - tasks located in the tail are less likely cache-hot,
   therefore the can_migrate_task() decision is higher.

hackbench illustrates slightly better performance. For example
doing 1000 samples and 40 groups on i5-3320M CPU, it shows below
figures:

 default: 0.657 avg
 patched: 0.646 avg

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/20170913102430.8985-2-urezki@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ac6602c..cc0bfb0 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6628,10 +6628,7 @@ again:
                set_next_entity(cfs_rq, se);
        }
 
-       if (hrtick_enabled(rq))
-               hrtick_start_fair(rq, p);
-
-       return p;
+       goto done;
 simple:
 #endif
 
@@ -6645,6 +6642,16 @@ simple:
 
        p = task_of(se);
 
+done: __maybe_unused
+#ifdef CONFIG_SMP
+       /*
+        * Move the next running task to the front of
+        * the list, so our cfs_tasks list becomes MRU
+        * one.
+        */
+       list_move(&p->se.group_node, &rq->cfs_tasks);
+#endif
+
        if (hrtick_enabled(rq))
                hrtick_start_fair(rq, p);
 
@@ -7080,11 +7087,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
  */
 static struct task_struct *detach_one_task(struct lb_env *env)
 {
-       struct task_struct *p, *n;
+       struct task_struct *p;
 
        lockdep_assert_held(&env->src_rq->lock);
 
-       list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+       list_for_each_entry_reverse(p,
+                       &env->src_rq->cfs_tasks, se.group_node) {
                if (!can_migrate_task(p, env))
                        continue;
 
@@ -7130,7 +7138,7 @@ static int detach_tasks(struct lb_env *env)
                if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
                        break;
 
-               p = list_first_entry(tasks, struct task_struct, se.group_node);
+               p = list_last_entry(tasks, struct task_struct, se.group_node);
 
                env->loop++;
                /* We've more or less seen every task there is, call it quits */
@@ -7180,7 +7188,7 @@ static int detach_tasks(struct lb_env *env)
 
                continue;
 next:
-               list_move_tail(&p->se.group_node, tasks);
+               list_move(&p->se.group_node, tasks);
        }
 
        /*